Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 650 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2472. Min Range: -0.2472

Max Act: 0.2472. Min Act: -0.0000

Data Index: 1434587 (Python Code)

Max Activating Token Index: 313

Text #1

Max Range: 0.2472. Min Range: -0.2472

Max Act: 0.2322. Min Act: -0.0001

Data Index: 1624682 (Python Code)

Max Activating Token Index: 815

Text #2

Max Range: 0.2472. Min Range: -0.2472

Max Act: 0.2249. Min Act: -0.0001

Data Index: 305327 (C4 (Web Text))

Max Activating Token Index: 295

Text #3

Max Range: 0.2472. Min Range: -0.2472

Max Act: 0.2243. Min Act: -0.0001

Data Index: 60125 (C4 (Web Text))

Max Activating Token Index: 747

Text #4

Max Range: 0.2472. Min Range: -0.2472

Max Act: 0.2305. Min Act: -0.0001

Data Index: 1385866 (Python Code)

Max Activating Token Index: 471

Text #5

Max Range: 0.2472. Min Range: -0.2472

Max Act: 0.2295. Min Act: -0.0001

Data Index: 1626238 (Python Code)

Max Activating Token Index: 817

Text #6

Max Range: 0.2472. Min Range: -0.2472

Max Act: 0.2266. Min Act: -0.0001

Data Index: 159013 (C4 (Web Text))

Max Activating Token Index: 882

Text #7

Max Range: 0.2472. Min Range: -0.2472

Max Act: 0.2249. Min Act: -0.0001

Data Index: 1581084 (Python Code)

Max Activating Token Index: 761

Text #8

Max Range: 0.2472. Min Range: -0.2472

Max Act: 0.2238. Min Act: -0.0001

Data Index: 907781 (C4 (Web Text))

Max Activating Token Index: 810

Text #9

Max Range: 0.2472. Min Range: -0.2472

Max Act: 0.2221. Min Act: -0.0001

Data Index: 14260 (C4 (Web Text))

Max Activating Token Index: 423

Text #10

Max Range: 0.2472. Min Range: -0.2472

Max Act: 0.2224. Min Act: -0.0001

Data Index: 1374219 (Python Code)

Max Activating Token Index: 91

Text #11

Max Range: 0.2472. Min Range: -0.2472

Max Act: 0.2219. Min Act: -0.0000

Data Index: 1463516 (Python Code)

Max Activating Token Index: 35

Text #12

Max Range: 0.2472. Min Range: -0.2472

Max Act: 0.2218. Min Act: -0.0001

Data Index: 1641738 (Python Code)

Max Activating Token Index: 20

Text #13

Max Range: 0.2472. Min Range: -0.2472

Max Act: 0.2266. Min Act: -0.0001

Data Index: 1466746 (Python Code)

Max Activating Token Index: 855

Text #14

Max Range: 0.2472. Min Range: -0.2472

Max Act: 0.2189. Min Act: -0.0000

Data Index: 1633225 (Python Code)

Max Activating Token Index: 651

Text #15

Max Range: 0.2472. Min Range: -0.2472

Max Act: 0.2156. Min Act: -0.0001

Data Index: 1289406 (C4 (Web Text))

Max Activating Token Index: 226

Text #16

Max Range: 0.2472. Min Range: -0.2472

Max Act: 0.2143. Min Act: -0.0001

Data Index: 1622971 (Python Code)

Max Activating Token Index: 372

Text #17

Max Range: 0.2472. Min Range: -0.2472

Max Act: 0.2129. Min Act: -0.0001

Data Index: 1380776 (Python Code)

Max Activating Token Index: 618

Text #18

Max Range: 0.2472. Min Range: -0.2472

Max Act: 0.2112. Min Act: -0.0001

Data Index: 1536425 (Python Code)

Max Activating Token Index: 885

Text #19

Max Range: 0.2472. Min Range: -0.2472

Max Act: 0.2124. Min Act: -0.0001

Data Index: 1153293 (C4 (Web Text))

Max Activating Token Index: 562